Optimalisasi Kinerja Unreal Engine 5 Menggunakan Teknik Meta-Learning untuk Rendering Real-Time dan Adaptasi AI
DOI:
https://doi.org/10.52436/1.jpti.444Keywords:
AI adaptif, Meta-learning, optimasi asset, rendering real-time, Unreal Engine 5Abstract
Penelitian ini mengeksplorasi penerapan teknik meta-learning untuk mengoptimalkan kinerja Unreal Engine 5, sebuah platform yang banyak digunakan dalam pengembangan game dan pembuatan 3D real-time. Meta-learning, yang sering disebut sebagai pembelajaran untuk belajar, berfokus pada pengembangan model yang dapat beradaptasi dengan tugas baru dengan data dan waktu pelatihan yang minimal. Penelitian ini bertujuan meningkatkan efisiensi rendering aset, optimasi scene, dan perilaku AI dalam lingkungan Unreal Engine 5. Dengan pendekatan meta-learning, kami berharap mencapai konvergensi yang lebih cepat dan generalisasi yang lebih baik di berbagai tugas, sehingga mengurangi beban komputasi. Metodologi penelitian melibatkan analisis komparatif antara model pembelajaran mesin tradisional dengan model meta-learning yang diterapkan pada manajemen aset dan rendering scene dinamis di Unreal Engine 5. Hasil penelitian menunjukkan bahwa model meta-learning memiliki kemampuan adaptasi dan efisiensi kinerja yang lebih baik, terutama pada skenario konten dinamis. Penelitian ini berkontribusi pada optimasi pipeline rendering real-time dalam pengembangan game, serta memberikan wawasan bagi pengembang yang ingin memanfaatkan AI untuk pengalaman pengguna yang lebih baik.
Downloads
References
Kopanas, G., Philip, J., Leimkühler, T., & Drettakis, G., "Point?Based Neural Rendering with Per?View Optimization," Computer Graphics Forum, vol. 40, 2021. doi: 10.1111/cgf.14339.
Landro, N., Gallo, I., & Grassa, R., "Combining Optimization Methods Using an Adaptive Meta Optimizer," Algorithms, vol. 14, 186, 2021. doi: 10.3390/a14060186.
Ba?anin, N., Stoean, C., Zivkovic, M., Jovanovic, D., Antonijevic, M., & Mladenovic, D., "Multi-Swarm Algorithm for Extreme Learning Machine Optimization," Sensors, vol. 22, 2022. doi: 10.3390/s22114204.
Li, Y., Shao, Z., Huang, X., Cai, B., & Peng, S., "Meta-FSEO: A Meta-Learning Fast Adaptation with Self-Supervised Embedding Optimization for Few-Shot Remote Sensing Scene Classification," Remote Sensing, vol. 13, 2776, 2021. doi: 10.3390/rs13142776.
Surianarayanan, C., Lawrence, J., Chelliah, P., Prakash, E., & Hewage, C., "A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)," Sensors, vol. 23, 2023. doi: 10.3390/s23031279.
He, Z., Chen, C., Li, L., Zheng, S., & Situ, H., "Quantum Architecture Search with Meta?Learning," Advanced Quantum Technologies, vol. 5, 2021. doi: 10.1002/qute.202100134.
Abbas, F., Zhang, F., Ismail, M., Khan, G., Iqbal, J., Alrefaei, A., & Albeshr, M., "Optimizing Machine Learning Algorithms for Landslide Susceptibility Mapping along the Karakoram Highway, Gilgit Baltistan, Pakistan: A Comparative Study of Baseline, Bayesian, and Metaheuristic Hyperparameter Optimization Techniques," Sensors, vol. 23, 2023. doi: 10.3390/s23156843.
Poiani, R., Tirinzoni, A., & Restelli, M., "Meta-Reinforcement Learning by Tracking Task Non-stationarity," Proceedings of the IJCAI, pp. 2899-2905, 2021. doi: 10.24963/ijcai.2021/399.
Li, J., Zhan, Z., Tan, K., & Zhang, J., "A Meta-Knowledge Transfer-Based Differential Evolution for Multitask Optimization," IEEE Transactions on Evolutionary Computation, vol. 26, pp. 719-734, 2022. doi: 10.1109/tevc.2021.3131236.
Eversberg, L., & Lambrecht, J., "Generating Images with Physics-Based Rendering for an Industrial Object Detection Task: Realism versus Domain Randomization," Sensors, vol. 21, 2021. doi: 10.3390/s21237901.
Lange, R., Schaul, T., Chen, Y., Zahavy, T., Dallibard, V., Lu, C., Singh, S., & Flennerhag, S., "Discovering Evolution Strategies via Meta-Black-Box Optimization," Proceedings of the Companion Conference on Genetic and Evolutionary Computation, 2022. doi: 10.1145/3583133.3595822.
Abdolrasol, M., Hussain, S., Ustun, T., Sarker, M., Hannan, M., Mohamed, R., Ali, J., Mekhilef, S., & Milad, A., "Artificial Neural Networks Based Optimization Techniques: A Review," Electronics, vol. 10, 2021. doi: 10.3390/electronics10212689.
Richards, S., Azizan, N., Slotine, J., & Pavone, M., "Control-oriented meta-learning," The International Journal of Robotics Research, vol. 42, pp. 777-797, 2022. doi: 10.1177/02783649231165085.
Han, C., Fan, Z., Zhang, D., Qiu, M., Gao, M., & Zhou, A., "Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification," ArXiv, abs/2107.12262, 2021. doi: 10.18653/v1/2021.findings-acl.145.
Zhang, P., Li, J., Wang, Y., & Pan, J., "Domain Adaptation for Medical Image Segmentation: A Meta-Learning Method," Journal of Imaging, vol. 7, 2021. doi: 10.3390/jimaging7020031.
Zhan, R., Liu, X., Wong, D., & Chao, L., "Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation," Proceedings of the AAAI, pp. 14310-14318, 2021. doi: 10.1609/aaai.v35i16.17683.
Langedijk, A., Dankers, V., Lippe, P., Bos, S., Guevara, B., Yannakoudakis, H., & Shutova, E., "Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing," ArXiv, abs/2104.04736, 2021. doi: 10.18653/v1/2022.acl-long.582.
Mudigere, D., Hao, Y., Huang, J., Jia, Z., Tulloch, A., Sridharan, S., Liu, X., Ozdal, M., Nie, J., Park, J., Luo, L., Yang, J., Gao, L., Ivchenko, D., Basant, A., Hu, Y., Yang, J., Ardestani, E., Wang, X., Komuravelli, R., Chu, C., Yilmaz, S., Li, H., Qian, J., Feng, Z., Ma, Y., Yang, J., Wen, E., Li, H., Yang, L., Sun, C., Zhao, W., Melts, D., Dhulipala, K., Kishore, K., Graf, T., Eisenman, A., Matam, K., Gangidi, A., Chen, G., Krishnan, M., Nayak, A., Nair, K., Muthiah, B., Khorashadi, M., Bhattacharya, P., Lapukhov, P., Naumov, M., Mathews, A., Qiao, L., Smelyanskiy, M., Jia, B., & Rao, V., "Software-hardware co-design for fast and scalable training of deep learning recommendation models," Proceedings of the 49th Annual International Symposium on Computer Architecture, 2021. doi: 10.1145/3470496.3533727.
Churchill, D., Lin, Z., & Synnaeve, G., "An Analysis of Model-Based Heuristic Search Techniques for StarCraft Combat Scenarios," Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2021. doi: 10.1609/aiide.v13i2.12962.
Zhao, T., Luo, J., Sushkov, O., Pevceviciute, R., Heess, N., Scholz, J., Schaal, S., & Levine, S., "Offline Meta-Reinforcement Learning for Industrial Insertion," 2022 International Conference on Robotics and Automation (ICRA), pp. 6386-6393, 2021. doi: 10.1109/icra46639.2022.9812312.
Lee, H., Vu, N., & Li, S., "Meta Learning and Its Applications to Natural Language Processing," Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts, 2021. doi: 10.18653/v1/2021.acl-tutorials.3.
F. Sadeghi, A. Larijani, O. Rostami, D. Martín, and P. Hajirahimi, "A novel multi-objective binary chimp optimization algorithm for optimal feature selection: Application of deep-learning-based approaches for SAR image classification," Sensors (Basel, Switzerland), vol. 23, p. 1180, 2023, doi: 10.3390/s23031180.
C. Zhao, F. Chen, and B. Thuraisingham, "Fairness-aware online meta-learning," Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, doi: 10.1145/3447548.3467389.
S. Yue, J. Ren, J. Xin, D. Zhang, Y. Zhang, and W. Zhuang, "Efficient federated meta-learning over multi-access wireless networks," IEEE Journal on Selected Areas in Communications, vol. 40, pp. 1556-1570, 2022, doi: 10.1109/jsac.2022.3143259.
S. Wang, H. Jia, L. Abualigah, Q. Liu, and R. Zheng, "An improved hybrid Aquila optimizer and Harris Hawks algorithm for solving industrial engineering optimization problems," Processes, vol. 9, p. 1551, 2021, doi: 10.3390/pr9091551.
R. Xie, Y. Wang, R. Wang, Y. Lu, Y. Zou, F. Xia, and L. Lin, "Long short-term temporal meta-learning in online recommendation," Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, 2021, doi: 10.1145/3488560.3498371.
L. Abualigah, A. Gandomi, M. Elaziz, H. Hamad, M. Omari, M. Alshinwan, and A. Khasawneh, "Advances in meta-heuristic optimization algorithms in big data text clustering," Electronics, vol. 10, p. 101, 2021, doi: 10.3390/electronics10020101.
R. Epps, A. Volk, K. Reyes, and M. Abolhasani, "Accelerated AI development for autonomous materials synthesis in flow," Chemical Science, vol. 12, pp. 6025-6036, 2021, doi: 10.1039/d0sc06463g.
J. Fan, Y. Li, and T. Wang, "An improved African vultures optimization algorithm based on tent chaotic mapping and time-varying mechanism," PLoS ONE, vol. 16, 2021, doi: 10.1371/journal.pone.0260725.
B. Zhang, X. Li, Y. Ye, S. Feng, and R. Ye, "MetaNODE: Prototype optimization as a neural ODE for few-shot learning," AAAI Conference on Artificial Intelligence, vol. 36, pp. 9014-9021, 2021, doi: 10.1609/aaai.v36i8.20885.
